CN109947510A - A kind of interface recommended method and device, computer equipment - Google Patents
A kind of interface recommended method and device, computer equipment Download PDFInfo
- Publication number
- CN109947510A CN109947510A CN201910196544.2A CN201910196544A CN109947510A CN 109947510 A CN109947510 A CN 109947510A CN 201910196544 A CN201910196544 A CN 201910196544A CN 109947510 A CN109947510 A CN 109947510A
- Authority
- CN
- China
- Prior art keywords
- target object
- showing interface
- interface effect
- age
- attribute information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Abstract
This application discloses a kind of interface recommended method and devices, computer equipment, which comprises acquires the image of target object；The customer attribute information of the target object is obtained from the image of the target object；Based on the customer attribute information of the target object, recommend the showing interface effect of target application for the target object.
Description
Technical field
This application involves processing technology of interface more particularly to a kind of interface recommended method and devices, computer equipment.
Background technique
The showing interface effect of application refers to the visual appearance of application, can usually be known as the showing interface effect of application
" skin " of application, different showing interface effects can have different themes, background colour etc..In order to allow user to have more preferably
Usage experience, often an application can provide multiple showing interface effects, i.e., more set skins are selected for user.Do not have in user
In the case where selection interface bandwagon effect, using will be shown with the showing interface effect of default.The interface of current application
The individual character that bandwagon effect is not bound with user is accurately recommended, and causes the usage experience of user poor, or even can reduce use
The viscosity at family.
Apply for content
In order to solve the above technical problems, the embodiment of the present application provides a kind of interface recommended method and device, computer are set
It is standby.
Interface recommended method provided by the embodiments of the present application, comprising:
Acquire the image of target object；
The customer attribute information of the target object is obtained from the image of the target object；
Based on the customer attribute information of the target object, recommend the showing interface effect of target application for the target object
Fruit.
In the embodiment of the present application, the user property letter that the target object is obtained from the image of the target object
Breath, comprising:
Facial image is obtained from the image of the target object；
The facial image is analyzed, determines following at least one customer attribute information of the target object: kind
Race's information, gender information, age information, expression information, identification information.
It is described that the facial image is analyzed in the embodiment of the present application, determine the age information of the target object,
Include:
The facial image is analyzed, obtain the facial image estimates the age；
According to it is described estimate the age and with it is described estimate the age there are preset two or the above age gap away from
Age, from the image pattern set at known age choose N width image pattern, the N be not less than 2；
Obtain the age size comparison result between the facial image and the N width image pattern of selection；
Probabilistic information is obtained according to the statistical information that the comparison result is formed, the probabilistic information is for determining the people
The age information of target object in face image.
In the embodiment of the present application, the statistical information formed according to the comparison result obtains probabilistic information, comprising:
According to preset first facial age prior probability distribution and based on the comparison result formed the first likelihood letter
Number obtains first facial age Posterior probability distribution；Wherein, described in the first facial age Posterior probability distribution is used to determine
The age information of target object in facial image.
Described to analyze the facial image in the embodiment of the present application, obtain the facial image estimates the age,
Include:
The facial image is inputted into neural network model, according to the determination of the output information of the neural network model
Facial image estimates the age.
In the embodiment of the present application, processing operation performed by the facial image of the neural network model for input
Include:
Obtain the facial characteristics of the people in the facial image；
For at least one preset age categories, judge that the facial characteristics belongs to the face more than the age categories
The probability of portion's feature, the probability form the likelihood value of the second likelihood function；
According to the preset second facial age prior probability distribution and the second likelihood function formed based on the probability
Generate the second facial age Posterior probability distribution；Wherein, the described second facial age Posterior probability distribution is for determining the people
Face image estimates the age.
In the embodiment of the present application, the customer attribute information based on the target object is recommended for the target object
The showing interface effect of target application, comprising:
In the corresponding multiple showing interface effects of target application, the customer attribute information phase with the target object is searched
Matched N number of showing interface effect, N >=1；
N number of showing interface effect is recommended into the target object.
The corresponding temperature category of each showing interface effect in the embodiment of the present application, in N number of showing interface effect
Property information, the temperature attribute information based on the showing interface effect frequency of usage determine；
It is described that N number of showing interface effect is recommended into the target object, comprising:
The target object is recommended after N number of showing interface effect is ranked up according to temperature attribute information.
In the embodiment of the present application, the corresponding scoring of each showing interface effect in N number of showing interface effect belongs to
Property information, user's scoring determination that the scoring attribute information is obtained based on the showing interface effect；
It is described that N number of showing interface effect is recommended into the target object, comprising:
The target object is recommended after N number of showing interface effect is ranked up according to scoring attribute information.
In the embodiment of the present application, the customer attribute information based on the target object is recommended for the target object
The showing interface effect of target application, comprising:
In the corresponding multiple showing interface effects of target application, the customer attribute information phase with the target object is searched
Matched N number of showing interface effect, N >=1；
M showing interface effect in N number of showing interface effect is recommended into the target object, 1≤M < N.
The corresponding temperature category of each showing interface effect in the embodiment of the present application, in N number of showing interface effect
Property information, the temperature attribute information based on the showing interface effect frequency of usage determine；
The M showing interface effect by N number of showing interface effect recommends the target object, comprising:
The maximum M showing interface effect of temperature attribute information is chosen from N number of showing interface effect；
The target object is recommended after the M showing interface effect is ranked up according to temperature attribute information.
In the embodiment of the present application, the corresponding scoring of each showing interface effect in N number of showing interface effect belongs to
Property information, user's scoring determination that the scoring attribute information is obtained based on the showing interface effect；
The M showing interface effect by N number of showing interface effect recommends the target object, comprising:
The scoring maximum M showing interface effect of attribute information is chosen from N number of showing interface effect；
The target object is recommended after the M showing interface effect is ranked up according to scoring attribute information.
In the embodiment of the present application, the customer attribute information based on the target object is recommended for the target object
The showing interface effect of target application, comprising:
Of the corresponding multiple showing interface effects of target application is determined according to the customer attribute information of the target object
With fractional value；
The matching maximum L showing interface effect of fractional value, L >=1 are chosen from the multiple showing interface effect；
The L showing interface effect is recommended into the target object.
It is described that the L showing interface effect is recommended into the target object in the embodiment of the present application, comprising:
The target object is recommended after the L showing interface effect is ranked up according to matching fractional value.
In the embodiment of the present application, the number for the showing interface effect of the target application of target object recommendation is more
It is a；The method also includes:
The first operation is obtained, first operation from multiple showing interface effects of recommendation for selecting an interface exhibition
Show effect, as target interface bandwagon effect；
The target application is shown according to the target interface bandwagon effect.
In the embodiment of the present application, the number for the showing interface effect of the target application of target object recommendation is one
It is a；The method also includes:
The target application is shown according to the showing interface effect of recommendation.
Interface recommendation apparatus provided by the embodiments of the present application, comprising:
Acquisition unit, for acquiring the image of target object；
First acquisition unit, the user property for obtaining the target object from the image of the target object are believed
Breath；
Recommendation unit recommends target to answer for the customer attribute information based on the target object for the target object
Showing interface effect.
In the embodiment of the present application, the first acquisition unit is used for:
Facial image is obtained from the image of the target object；
The facial image is analyzed, determines following at least one customer attribute information of the target object: kind
Race's information, gender information, age information, expression information, identification information.
In the embodiment of the present application, the first acquisition unit is used for:
The facial image is analyzed, obtain the facial image estimates the age；
According to it is described estimate the age and with it is described estimate the age there are preset two or the above age gap away from
Age, from the image pattern set at known age choose N width image pattern, the N be not less than 2；
Obtain the age size comparison result between the facial image and the N width image pattern of selection；
Probabilistic information is obtained according to the statistical information that the comparison result is formed, the probabilistic information is for determining the people
The age information of target object in face image.
In the embodiment of the present application, the first acquisition unit is used for:
According to preset first facial age prior probability distribution and based on the comparison result formed the first likelihood letter
Number obtains first facial age Posterior probability distribution；Wherein, described in the first facial age Posterior probability distribution is used to determine
The age information of target object in facial image.
In the embodiment of the present application, the first acquisition unit is used for: the facial image is inputted into neural network model,
The age is estimated according to what the output information of the neural network model determined the facial image.
In the embodiment of the present application, the neural network model includes:
Second acquisition unit, for obtaining the facial characteristics of the people in the facial image；
Judging unit, for being directed at least one preset age categories, judging that the facial characteristics belongs to is more than
The probability of the facial characteristics of the age categories, the probability form the likelihood value of the second likelihood function；
Generation unit, for what is formed according to the preset second facial age prior probability distribution and based on the probability
Second likelihood function generates the second facial age Posterior probability distribution；Wherein, the described second facial age Posterior probability distribution is used
The age is estimated in determine the facial image.
In the embodiment of the present application, the recommendation unit is used for:
In the corresponding multiple showing interface effects of target application, the customer attribute information phase with the target object is searched
Matched N number of showing interface effect, N >=1；
N number of showing interface effect is recommended into the target object.
The corresponding temperature category of each showing interface effect in the embodiment of the present application, in N number of showing interface effect
Property information, the temperature attribute information based on the showing interface effect frequency of usage determine；
The recommendation unit, is used for: recommending after N number of showing interface effect is ranked up according to temperature attribute information
To the target object.
In the embodiment of the present application, the corresponding scoring of each showing interface effect in N number of showing interface effect belongs to
Property information, user's scoring determination that the scoring attribute information is obtained based on the showing interface effect；
The recommendation unit, is used for: recommending after N number of showing interface effect is ranked up according to scoring attribute information
To the target object.
In the embodiment of the present application, the recommendation unit is used for:
In the corresponding multiple showing interface effects of target application, the customer attribute information phase with the target object is searched
Matched N number of showing interface effect, N >=1；
M showing interface effect in N number of showing interface effect is recommended into the target object, 1≤M < N.
The corresponding temperature category of each showing interface effect in the embodiment of the present application, in N number of showing interface effect
Property information, the temperature attribute information based on the showing interface effect frequency of usage determine；
The recommendation unit, is used for: the maximum M boundary of temperature attribute information is chosen from N number of showing interface effect
Face bandwagon effect；The target object is recommended after the M showing interface effect is ranked up according to temperature attribute information.
In the embodiment of the present application, the corresponding scoring of each showing interface effect in N number of showing interface effect belongs to
Property information, user's scoring determination that the scoring attribute information is obtained based on the showing interface effect；
The recommendation unit, is used for: the scoring maximum M boundary of attribute information is chosen from N number of showing interface effect
Face bandwagon effect；The target object is recommended after the M showing interface effect is ranked up according to scoring attribute information.
In the embodiment of the present application, the recommendation unit is used for:
Of the corresponding multiple showing interface effects of target application is determined according to the customer attribute information of the target object
With fractional value；
The matching maximum L showing interface effect of fractional value, L >=1 are chosen from the multiple showing interface effect；
The L showing interface effect is recommended into the target object.
In the embodiment of the present application, the recommendation unit is used for: by the L showing interface effect according to matching fractional value
The target object is recommended after being ranked up.
In the embodiment of the present application, the number for the showing interface effect of the target application of target object recommendation is more
It is a；Described device further include:
Third acquiring unit, for obtaining the first operation, first operation from multiple showing interfaces of recommendation for imitating
A showing interface effect is selected in fruit, as target interface bandwagon effect；
Display unit, for showing the target application according to the target interface bandwagon effect.
In the embodiment of the present application, the number for the showing interface effect of the target application of target object recommendation is one
It is a；Described device further include:
Display unit, for showing the target application according to the showing interface effect of recommendation.
Computer program product provided by the embodiments of the present application includes computer executable instructions, and the computer is executable to be referred to
After order is performed, above-mentioned interface recommended method can be realized.
It is stored with executable instruction on storage medium provided by the embodiments of the present application, which is executed by processor
Shi Shixian above-mentioned interface recommended method.
Computer equipment provided by the embodiments of the present application includes memory and processor, and calculating is stored on the memory
Machine executable instruction can realize that above-mentioned interface pushes away when the processor runs the computer executable instructions on the memory
Recommend method.
In the technical solution of the embodiment of the present application, the image of target object is acquired；It is obtained from the image of the target object
Take the customer attribute information of the target object；Based on the customer attribute information of the target object, pushed away for the target object
Recommend the showing interface effect of target application.Using the technical solution of the embodiment of the present application, the individual character in conjunction with user is that user is accurate
The showing interface effect of target application is recommended to improve user to improve the usage experience of user and glue to target application in ground
Property.
Detailed description of the invention
Fig. 1 is the flow diagram one of interface recommended method provided by the embodiments of the present application；
Fig. 2 is the recommendation interface schematic diagram one of showing interface effect provided by the embodiments of the present application；
Fig. 3 is the flow diagram two of interface recommended method provided by the embodiments of the present application；
Fig. 4 (a) is the recommendation interface schematic diagram two of showing interface effect provided by the embodiments of the present application；
Fig. 4 (b) is the recommendation interface schematic diagram three of showing interface effect provided by the embodiments of the present application；
Fig. 5 is the flow diagram three of interface recommended method provided by the embodiments of the present application；
Fig. 6 is the flow diagram four of interface recommended method provided by the embodiments of the present application；
Fig. 7 is the structure composition schematic diagram of interface recommendation apparatus provided by the embodiments of the present application；
Fig. 8 is the structure composition schematic diagram of the computer equipment of the embodiment of the present application.
Specific embodiment
The various exemplary embodiments of the application are described in detail now with reference to attached drawing.It should also be noted that unless in addition having
Body explanation, the unlimited system of component and the positioned opposite of step, numerical expression and the numerical value otherwise illustrated in these embodiments is originally
The range of application.
Simultaneously, it should be appreciated that for ease of description, the size of various pieces shown in attached drawing is not according to reality
Proportionate relationship draw.
Be to the description only actually of at least one exemplary embodiment below it is illustrative, never as to the application
And its application or any restrictions used.
Technology, method and apparatus known to person of ordinary skill in the relevant may be not discussed in detail, but suitable
In the case of, the technology, method and apparatus should be considered as part of specification.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, then in subsequent attached drawing does not need that it is further discussed.
The embodiment of the present application can be applied to the terminal devices such as fixed terminal/mobile terminal, such as: somatic sensation television game machine, mutually
Dynamic advertisement machine, mobile phone, tablet computer, game machine, desktop computer, all-in-one machine, car-mounted terminal etc..In the embodiment of the present application, should
Terminal device can also be wearable device.Wearable device is referred to as wearable intelligent equipment, is using wearable skill
Art carries out intelligentized design to daily wearing, develops the general name of the equipment that can be dressed, as glasses, gloves, wrist-watch, dress ornament and
Shoes etc..Wearable device is directly worn, or is integrated into the clothes of user or a kind of portable device of accessory.It can wear
Wearing equipment is not only a kind of hardware device, is even more interacted by software support and data interaction, cloud powerful to realize
Function.Broad sense wearable intelligent equipment, which includes that function is complete, size is big, can not depend on smart phone, realizes complete or partial function
Can, such as: smartwatch or intelligent glasses etc., and only it is absorbed in certain a kind of application function, it needs and other equipment such as intelligence
Mobile phone is used cooperatively, such as Intelligent bracelet, the intelligent jewellery of all kinds of carry out sign monitorings.
Fig. 1 is the flow diagram one of interface recommended method provided by the embodiments of the present application, as shown in Figure 1, the interface
Recommended method the following steps are included:
Step 101: acquiring the image of target object.
In the embodiment of the present application, target object refers to some user, can by but be not limited to following manner acquire mesh
It marks the image of object: target object being shot by camera, obtains the image of the target object.It, can when specific implementation
To carry out captured in real-time to target object, video sequence is obtained, the video sequence includes multiple image, in the video sequence
Any one frame image all can serve as the image of the target object.Alternatively, shooting to target object, a frame figure is obtained
Picture, using this frame image as the image of the target object.
Here, camera can be 2D camera, be also possible to 3D camera.Correspondingly, the collected figure of 2D camera
As being 2D image, 3D camera acquired image is 3D rendering.
Step 102: the customer attribute information of the target object is obtained from the image of the target object.
In the embodiment of the present application, facial image is obtained from the image of the target object；Then, to the facial image
It is analyzed, determines following at least one customer attribute information of the target object: ethnic information, gender information, age letter
Breath, expression information, identification information.
In an application scenarios, the nerve net of profile information or key point information for extracting facial image can be passed through
Network demarcates the profile of facial image.Specifically, the image of target object is input in neural network, from the neural network
The profile information or key point information of facial image are obtained in output information.Then, the profile information based on facial image or pass
Key point information is partitioned into facial image from the image of the target object.
In the embodiment of the present application, one or more customer attribute informations are analyzed from facial image.Below to not of the same race
The customer attribute information of class is described.
1) ethnic information
The colour of skin for analyzing face in facial image, determines the ethnic information of target object.Such as: the yellow colour of skin is corresponding yellow
Kind people, the white colour of skin correspond to white people, and the black colour of skin corresponds to black race.
2) gender information
The face and overall profile for analyzing face in facial image, determine the gender of target object, here it is possible to according to
The facial characteristics of facial image determines the gender of target object.In one embodiment, the image of target object is input to mind
Through obtaining the facial characteristics of facial image from the output information of the neural network in network.Then, based on the face of facial image
Portion's feature determines the gender of target object.
3) age information
Here, such as the age information of target object can be obtained in the following manner: the facial image is divided
Analysis, obtain the facial image estimates the age；According to it is described estimate the age and with it is described estimate the age exist preset
Two or the above age gap away from age, from the image pattern set at known age choose N width image pattern, the N
Not less than 2；Obtain the age size comparison result between the facial image and the N width image pattern of selection；According to institute
The statistical information for stating comparison result formation obtains probabilistic information, and the probabilistic information is for determining target pair in the facial image
The age information of elephant.Here it is possible to according to preset first facial age prior probability distribution and result shape based on the comparison
At the first likelihood function obtain first facial age Posterior probability distribution；Wherein, the first facial age posterior probability point
Cloth is used to determine the age information of target object in the facial image.
Specifically, the age is estimated using the facial image (image such as to be marked), estimates the age with this to choose
With certain age gap away from age corresponding image pattern, and obtain the age size ratio between facial image and image pattern
Compared with as a result, due to the age between age size comparison result and the image pattern of facial image estimating the age and selecting
Gap meets likelihood function (for example, logistic function), and therefore, the age size comparison result of the embodiment of the present application can be with shape
At likelihood function, so that the embodiment of the present application, which can use total probability formula, makes likelihood function and facial age prior probability distribution
Form facial age Posterior probability distribution；And then face can be reasonably inferred to based on facial age Posterior probability distribution is objective
The facial age (i.e. the age information of target object) of people in image.
In addition, the embodiment of the present application can use neural network model to obtain the age of estimating of the facial image, have
Body, the facial image is inputted into neural network model, the people is determined according to the output information of the neural network model
Face image estimates the age.Further, processing behaviour performed by the facial image of the neural network model for input
Work includes: the facial characteristics for obtaining the people in the facial image；For at least one preset age categories, institute is judged
The probability for the facial characteristics that facial characteristics belongs to more than the age categories is stated, the probability forms the likelihood of the second likelihood function
Value；The is generated according to the preset second facial age prior probability distribution and the second likelihood function formed based on the probability
Two facial age Posterior probability distributions；Wherein, the described second facial age Posterior probability distribution is for determining the facial image
Estimate the age.
In above scheme, the facial characteristics of the people in facial image is obtained using neural network model, and for preparatory
At least one of setting (for example, each curtate age in 1-70 years old, for another example each curtate age in 1-100 years old at age
Deng) classification, to judge that the facial characteristics belongs to the probability of the facial characteristics more than the age categories, then neural network model can be with
The probability for obtaining it forms likelihood function, and then neural network model can use pre-set facial age prior probability
Distribution and above-mentioned likelihood function generate facial age Posterior probability distribution；If utilizing such facial age posterior probability point
Cloth determines facial age of the people in facial image, then may be implemented the age based on neural network model and estimate, and is advantageous
In the accuracy that the raising age is estimated；Further, if using the facial age determined based on neural network model as
Facial image estimates the age, then since the facial age determined based on neural network model is often more acurrate,
Selected from image pattern set with facial image have certain age gap away from image pattern often closer to objective
Situation, to be conducive to further increase the confidence level of the markup information of the image in image pattern set.
4) expression information
The face and overall profile for analyzing face in facial image, determine the expression of target object.Here, human face expression
Have: smile, laugh, is sad, dejected, amimia, surprised etc., different expressions will drive the face and overall profile hair of face
Raw different degrees of movement, face and overall profile based on face may determine that the expression of target object.
5) identification information
Facial image is identified, determines the identification information of target object.Here it is possible to the multiple use of typing in advance
The facial image at family is that the facial image of each user is arranged unique identification information, subsequent to newly getting
When facial image is identified, matching facial image can be searched in multiple facial images of typing, and obtain phase
The identification information answered.
Step 103: the customer attribute information based on the target object recommends the boundary of target application for the target object
Face bandwagon effect.
In the embodiment of the present application, target application can be third-party application, be also possible to system application.On the other hand, mesh
The type for marking application is unlimited, can be chat application, browser application, Video Applications, music application, game application etc..
In the embodiment of the present application, the user with same subscriber attribute information is classified as a user group, for mesh
Mark application designs the showing interface effects of different characteristics for different user groups, and here, different showing interface effects can be with
With different themes, background colour etc..In an application scenarios, different brands element can be merged in showing interface effect
In, as a kind of theme of characteristic, such as: showing interface effect is Spider-Man theme (being properly termed as Spider-Man skin), then example
If showing interface effect is Princess Barbie theme (being properly termed as Princess Barbie skin).
For example: target application is body-sensing interactive game, meets its customer attribute information for different player's configurations
Interface skin analyzes the facial image of the user, determines the user's when user starts body-sensing interactive game
Customer attribute information is that the user recommends the interface skin for meeting its interest preference based on the customer attribute information.
In the embodiment of the present application, different labels is stamped for different showing interface effects, it will according to customer attribute information
Different showing interface effects is directed to different user groups, such as: the matching of Spider-Man skin is " for men less than 20 years old
Family ", Princess Barbie skin match " female user less than 15 years old " etc..
In the embodiment of the present application, the number for the showing interface effect of the target application of target object recommendation is one
Or it is multiple；Wherein, in the case that 1) number of the showing interface effect for the target application recommended for the target object is one,
Directly the target application is shown according to the showing interface effect of recommendation.2) boundary for the target application recommended for the target object
In the case that the number of face bandwagon effect is multiple, the first operation is obtained, first operation is for from multiple interfaces of recommendation
A showing interface effect is selected in bandwagon effect, as target interface bandwagon effect；According to the target interface bandwagon effect
Show the target application.For example: referring to Fig. 2, the showing interface effect of recommendation includes showing interface effect 1, interface exhibition
Show effect 2, showing interface effect 3, these three showing interface effects are recommended into target object, target object is from these three interfaces
Selection interface bandwagon effect 2 shows target application in bandwagon effect.
The technical solution of the embodiment of the present application, so that target application has " adaptivity ", according to the user of target object
Attribute information is that the target object recommends suitable showing interface effect automatically.
Fig. 3 is the flow diagram two of interface recommended method provided by the embodiments of the present application, as shown in figure 3, the interface
Recommended method the following steps are included:
Step 301: acquiring the image of target object.
In the embodiment of the present application, target object refers to some user, can by but be not limited to following manner acquire mesh
It marks the image of object: target object being shot by camera, obtains the image of the target object.It, can when specific implementation
To carry out captured in real-time to target object, video sequence is obtained, the video sequence includes multiple image, in the video sequence
Any one frame image all can serve as the image of the target object.Alternatively, shooting to target object, a frame figure is obtained
Picture, using this frame image as the image of the target object.
Step 302: the customer attribute information of the target object is obtained from the image of the target object.
In the embodiment of the present application, facial image is obtained from the image of the target object；Then, to the facial image
It is analyzed, determines following at least one customer attribute information of the target object: ethnic information, gender information, age letter
Breath, expression information, identification information.
Step 303: in the corresponding multiple showing interface effects of target application, searching and belong to the user of the target object
N number of showing interface effect that property information matches, N >=1；N number of showing interface effect is recommended into the target object.
In the embodiment of the present application, target application can be third-party application, be also possible to system application.On the other hand, mesh
The type for marking application is unlimited, can be chat application, browser application, Video Applications, music application, game application etc..
In the embodiment of the present application, the user with same subscriber attribute information is classified as a user group, for mesh
Mark application designs the showing interface effects of different characteristics for different user groups, and here, different showing interface effects can be with
With different themes, background colour etc..In an application scenarios, different brands element can be merged in showing interface effect
In, as a kind of theme of characteristic, such as: showing interface effect is Spider-Man theme (being properly termed as Spider-Man skin), then example
If showing interface effect is Princess Barbie theme (being properly termed as Princess Barbie skin).
In the embodiment of the present application, different labels is stamped for different showing interface effects, it will according to customer attribute information
Different showing interface effects is directed to different user groups, such as: the matching of Spider-Man skin is " for men less than 30 years old
Family ", Princess Barbie skin match " female user less than 15 years old " etc..
In the embodiment of the present application, searches the N number of showing interface to match with the customer attribute information of the target object and imitate
After fruit, this N number of showing interface effect is all recommended into the target object.Here it is possible to recommend N number of boundary in the following manner
Face bandwagon effect:
Mode one: the corresponding temperature attribute information of each showing interface effect in N number of showing interface effect, institute
The frequency of usage that temperature attribute information is stated based on the showing interface effect determines；Based on this, by N number of showing interface effect
The target object is recommended after being ranked up according to temperature attribute information.
For example: the corresponding temperature attribute information of showing interface effect indicates that hot value can lead to by hot value
The frequency of usage of statistics interface bandwagon effect is crossed to determine, specifically, counts each interface exhibition of target application in some cycles
The download for showing effect, calculate the download of each showing interface effect relative to whole showing interface effects always download account for
Than as hot value.Referring to Fig. 4 (a), N=3, the showing interface effect of recommendation includes showing interface effect 1, showing interface effect
These three showing interface effects are ranked up by fruit 2, showing interface effect 3 according to hot value, and hot value is followed successively by from big to small
Showing interface effect 3, showing interface effect 1, showing interface effect 2.
Mode two: the corresponding scoring attribute information of each showing interface effect in N number of showing interface effect, institute
Commentary divides attribute information to determine based on user's scoring that the showing interface effect obtains；Based on this, by N number of showing interface
Effect recommends the target object after being ranked up according to scoring attribute information.
For example: the corresponding scoring attribute information of showing interface effect indicates that score value can lead to by score value
Counting user is crossed to the scoring of showing interface effect to determine, specifically, user is to showing interface effect in statistics some cycles
Average score, the score value as the showing interface effect.Referring to Fig. 4 (b), the showing interface effect of N=3, recommendation include
Showing interface effect 1, showing interface effect 2, showing interface effect 3, the corresponding score value B of showing interface effect 1, showing interface effect
Fruit 2 corresponds to score value C, showing interface effect 3 corresponding score value A, A > B > C, by these three showing interface effects according to scoring
Value is ranked up, and score value is followed successively by showing interface effect 3, showing interface effect 1, showing interface effect 2 from big to small.
In the embodiment of the present application, the number for the showing interface effect of the target application of target object recommendation is more
It is a, the first operation is obtained, first operation from multiple showing interface effects of recommendation for selecting a showing interface effect
Fruit, as target interface bandwagon effect；The target application is shown according to the target interface bandwagon effect.For example: ginseng
According to Fig. 2, the showing interface effect of recommendation includes showing interface effect 1, showing interface effect 2, showing interface effect 3, by this three
A showing interface effect recommends target object, target object selection interface bandwagon effect 2 from these three showing interface effects
To show target application.
The technical solution of the embodiment of the present application, so that target application has " adaptivity ", according to the user of target object
Attribute information is that the target object recommends suitable showing interface effect automatically.
Fig. 5 is the flow diagram three of interface recommended method provided by the embodiments of the present application, as shown in figure 5, the interface
Recommended method the following steps are included:
Step 501: acquiring the image of target object.
In the embodiment of the present application, target object refers to some user, can by but be not limited to following manner acquire mesh
It marks the image of object: target object being shot by camera, obtains the image of the target object.It, can when specific implementation
To carry out captured in real-time to target object, video sequence is obtained, the video sequence includes multiple image, in the video sequence
Any one frame image all can serve as the image of the target object.Alternatively, shooting to target object, a frame figure is obtained
Picture, using this frame image as the image of the target object.
Step 502: the customer attribute information of the target object is obtained from the image of the target object.
In the embodiment of the present application, facial image is obtained from the image of the target object；Then, to the facial image
It is analyzed, determines following at least one customer attribute information of the target object: ethnic information, gender information, age letter
Breath, expression information, identification information.
Step 503: in the corresponding multiple showing interface effects of target application, searching and belong to the user of the target object
N number of showing interface effect that property information matches, N >=1；M showing interface effect in N number of showing interface effect is pushed away
It recommends to the target object, 1≤M < N.
In the embodiment of the present application, target application can be third-party application, be also possible to system application.On the other hand, mesh
The type for marking application is unlimited, can be chat application, browser application, Video Applications, music application, game application etc..
In the embodiment of the present application, the user with same subscriber attribute information is classified as a user group, for mesh
Mark application designs the showing interface effects of different characteristics for different user groups, and here, different showing interface effects can be with
With different themes, background colour etc..In an application scenarios, different brands element can be merged in showing interface effect
In, as a kind of theme of characteristic, such as: showing interface effect is Spider-Man theme (being properly termed as Spider-Man skin), then example
If showing interface effect is Princess Barbie theme (being properly termed as Princess Barbie skin).
In the embodiment of the present application, different labels is stamped for different showing interface effects, it will according to customer attribute information
Different showing interface effects is directed to different user groups, such as: the matching of Spider-Man skin is " for men less than 50 years old
Family ", Princess Barbie skin match " female user less than 15 years old " etc..
In the embodiment of the present application, searches the N number of showing interface to match with the customer attribute information of the target object and imitate
After fruit, M showing interface effect in this N number of showing interface effect is recommended into the target object.Here it is possible to by with
Under type recommends M showing interface effect:
Mode one: the corresponding temperature attribute information of each showing interface effect in N number of showing interface effect, institute
The frequency of usage that temperature attribute information is stated based on the showing interface effect determines；Based on this, from N number of showing interface effect
The middle maximum M showing interface effect of selection temperature attribute information；By the M showing interface effect according to temperature attribute information
The target object is recommended after being ranked up.
For example: the corresponding temperature attribute information of showing interface effect indicates that hot value can lead to by hot value
The frequency of usage of statistics interface bandwagon effect is crossed to determine, specifically, counts each interface exhibition of target application in some cycles
The download for showing effect, calculate the download of each showing interface effect relative to whole showing interface effects always download account for
Than as hot value.Assuming that therefore N=6, M=3 choose maximum preceding 3 interfaces of hot value from 6 showing interface effects
Bandwagon effect, referring to Fig. 4 (a), including showing interface effect 1, showing interface effect 2, showing interface effect 3, by these three boundaries
Face bandwagon effect is ranked up according to hot value, hot value be followed successively by from big to small showing interface effect 3, showing interface effect 1,
Showing interface effect 2.
Mode two: the corresponding scoring attribute information of each showing interface effect in N number of showing interface effect, institute
Commentary divides attribute information to determine based on user's scoring that the showing interface effect obtains；Based on this, by the M showing interface
Effect recommends the target object after being ranked up according to scoring attribute information.
For example: the corresponding scoring attribute information of showing interface effect indicates that score value can lead to by score value
Counting user is crossed to the scoring of showing interface effect to determine, specifically, user is to showing interface effect in statistics some cycles
Average score, the score value as the showing interface effect.Assuming that N=6, M=3, therefore, from 6 showing interface effects
Choose the maximum preceding 3 showing interface effects of score value, referring to Fig. 4 (b), including showing interface effect 1, showing interface effect 2,
Showing interface effect 3, the corresponding score value B of showing interface effect 1, the corresponding score value C of showing interface effect 2, showing interface effect 3
These three showing interface effects are ranked up by corresponding score value A, A > B > C according to score value, and score value is from big to small successively
For showing interface effect 3, showing interface effect 1, showing interface effect 2.
In the embodiment of the present application, the number for the showing interface effect of the target application of target object recommendation is more
It is a, the first operation is obtained, first operation from multiple showing interface effects of recommendation for selecting a showing interface effect
Fruit, as target interface bandwagon effect；The target application is shown according to the target interface bandwagon effect.For example: ginseng
According to Fig. 2, the showing interface effect of recommendation includes showing interface effect 1, showing interface effect 2, showing interface effect 3, by this three
A showing interface effect recommends target object, target object selection interface bandwagon effect 2 from these three showing interface effects
To show target application.
The technical solution of the embodiment of the present application, so that target application has " adaptivity ", according to the user of target object
Attribute information is that the target object recommends suitable showing interface effect automatically.
Fig. 6 is the flow diagram four of interface recommended method provided by the embodiments of the present application, as shown in fig. 6, the interface
Recommended method the following steps are included:
Step 601: acquiring the image of target object.
In the embodiment of the present application, target object refers to some user, can by but be not limited to following manner acquire mesh
It marks the image of object: target object being shot by camera, obtains the image of the target object.It, can when specific implementation
To carry out captured in real-time to target object, video sequence is obtained, the video sequence includes multiple image, in the video sequence
Any one frame image all can serve as the image of the target object.Alternatively, shooting to target object, a frame figure is obtained
Picture, using this frame image as the image of the target object.
Step 602: the customer attribute information of the target object is obtained from the image of the target object.
In the embodiment of the present application, facial image is obtained from the image of the target object；Then, to the facial image
It is analyzed, determines following at least one customer attribute information of the target object: ethnic information, gender information, age letter
Breath, expression information, identification information.
Step 603: the corresponding multiple showing interfaces of target application are determined according to the customer attribute information of the target object
The matching fractional value of effect；The matching maximum L showing interface effect of fractional value is chosen from the multiple showing interface effect,
L≥1；The L showing interface effect is recommended into the target object.
In the embodiment of the present application, the target object has one or more customer attribute informations, is calculating some interface
When the matching fractional value of bandwagon effect, 1) calculate fractional value of each customer attribute information relative to the showing interface effect；2)
Processing is weighted to the fractional value of each customer attribute information, obtains the matching fractional value of the showing interface effect.As an example
Son: assuming that target object has 2 customer attribute informations, it is respectively as follows: gender information, age information, wherein gender information is opposite
It is T1 in the fractional value of showing interface effect 1, age information is T2 relative to the fractional value of showing interface effect 1；To T1 and T2
It is weighted place
Reason, the matching fractional value for obtaining showing interface effect 1 areWherein, siFor TiCorresponding weighting system
Number, the weighting coefficient of each customer attribute information can be pre-set.Based on this, calculate in the manner described above
Then the matching fractional value of each showing interface effect of target application chooses matching from the multiple showing interface effect
The maximum L showing interface effect of fractional value is recommended after being ranked up the L showing interface effect according to matching fractional value
To the target object.
For example: the spadger that target object is 10 years old, gender information are male, and age information is 10 years old；Target is answered
With there are two showing interface effects, respectively Spider-Man skin and Barbie doll skin.Calculate the matching score of Spider-Man skin
When value, gender information is T1=95, score of the age information relative to Spider-Man skin relative to the fractional value of Spider-Man skin
Value is T2=85, and the weighting coefficient that the weighting coefficient of T1 is 60%, T2 is 40%, it is seen then that the matching fractional value of Spider-Man skin
For 95 × 60%+85 × 40%=91；Similarly, when calculating the matching fractional value of Barbie doll skin, gender information is relative to fragrant plant
Fractional value than doll skin is T1=2, and age information is T2=85, the weighting of T1 relative to the fractional value of Barbie doll skin
The weighting coefficient that coefficient is 60%, T2 is 40%, it is seen then that the matching fractional value of Barbie doll skin is 2 × 60%+85 × 40%
=35.2.
In the embodiment of the present application, the number for the showing interface effect of the target application of target object recommendation is more
It is a, the first operation is obtained, first operation from multiple showing interface effects of recommendation for selecting a showing interface effect
Fruit, as target interface bandwagon effect；The target application is shown according to the target interface bandwagon effect.For example: ginseng
According to Fig. 2, the showing interface effect of recommendation includes showing interface effect 1, showing interface effect 2, showing interface effect 3, by this three
A showing interface effect recommends target object, target object selection interface bandwagon effect 2 from these three showing interface effects
To show target application.
The technical solution of the embodiment of the present application, so that target application has " adaptivity ", according to the user of target object
Attribute information is that the target object recommends suitable showing interface effect automatically.
Fig. 7 is the structure composition schematic diagram of interface recommendation apparatus provided by the embodiments of the present application, as shown in fig. 7, the dress
It sets and includes:
Acquisition unit 701, for acquiring the image of target object；
First acquisition unit 702, for obtaining the user property of the target object from the image of the target object
Information；
Recommendation unit 703 recommends target for the customer attribute information based on the target object for the target object
The showing interface effect of application.
In one embodiment, the first acquisition unit 702, is used for:
Facial image is obtained from the image of the target object；
The facial image is analyzed, determines following at least one customer attribute information of the target object: kind
Race's information, gender information, age information, expression information, identification information.
In one embodiment, the first acquisition unit 702, is used for:
The facial image is analyzed, obtain the facial image estimates the age；
According to it is described estimate the age and with it is described estimate the age there are preset two or the above age gap away from
Age, from the image pattern set at known age choose N width image pattern, the N be not less than 2；
Obtain the age size comparison result between the facial image and the N width image pattern of selection；
Probabilistic information is obtained according to the statistical information that the comparison result is formed, the probabilistic information is for determining the people
The age information of target object in face image.
In one embodiment, the first acquisition unit 702, is used for: general according to preset first facial age priori
Rate distribution and the first likelihood function that result is formed based on the comparison obtain first facial age Posterior probability distribution；Wherein,
The first facial age Posterior probability distribution is used to determine the age information of target object in the facial image.
In one embodiment, the first acquisition unit 702, is used for: the facial image is inputted neural network mould
Type 704 estimates the age according to what the output information of the neural network model 704 determined the facial image.
In one embodiment, the neural network model 704 includes:
Second acquisition unit 7041, for obtaining the facial characteristics of the people in the facial image；
Judging unit 7042 judges that the facial characteristics belongs to for being directed at least one preset age categories
More than the probability of the facial characteristics of the age categories, the probability forms the likelihood value of the second likelihood function；
Generation unit 7043, for according to the preset second facial age prior probability distribution and based on the probability shape
At the second likelihood function generate the second facial age Posterior probability distribution；Wherein, the described second facial age posterior probability point
What cloth was used to determine the facial image estimates the age.
In one embodiment, the recommendation unit 703, is used for:
In the corresponding multiple showing interface effects of target application, the customer attribute information phase with the target object is searched
Matched N number of showing interface effect, N >=1；
N number of showing interface effect is recommended into the target object.
In one embodiment, the corresponding temperature category of each showing interface effect in N number of showing interface effect
Property information, the temperature attribute information based on the showing interface effect frequency of usage determine；
The recommendation unit 703, is used for: after N number of showing interface effect is ranked up according to temperature attribute information
Recommend the target object.
In one embodiment, the corresponding scoring of each showing interface effect in N number of showing interface effect belongs to
Property information, user's scoring determination that the scoring attribute information is obtained based on the showing interface effect；
The recommendation unit 703, is used for: after N number of showing interface effect is ranked up according to scoring attribute information
Recommend the target object.
In one embodiment, the recommendation unit 703, is used for:
In the corresponding multiple showing interface effects of target application, the customer attribute information phase with the target object is searched
Matched N number of showing interface effect, N >=1；
M showing interface effect in N number of showing interface effect is recommended into the target object, 1≤M < N.
In one embodiment, the corresponding temperature category of each showing interface effect in N number of showing interface effect
Property information, the temperature attribute information based on the showing interface effect frequency of usage determine；
The recommendation unit 703, is used for: the maximum M of temperature attribute information are chosen from N number of showing interface effect
Showing interface effect；The target pair is recommended after the M showing interface effect is ranked up according to temperature attribute information
As.
In one embodiment, the corresponding scoring of each showing interface effect in N number of showing interface effect belongs to
Property information, user's scoring determination that the scoring attribute information is obtained based on the showing interface effect；
The recommendation unit 703, is used for: scoring the maximum M of attribute information are chosen from N number of showing interface effect
Showing interface effect；The target pair is recommended after the M showing interface effect is ranked up according to scoring attribute information
As.
In one embodiment, the recommendation unit 703, is used for:
Of the corresponding multiple showing interface effects of target application is determined according to the customer attribute information of the target object
With fractional value；
The matching maximum L showing interface effect of fractional value, L >=1 are chosen from the multiple showing interface effect；
The L showing interface effect is recommended into the target object.
In one embodiment, the recommendation unit 703, is used for: by the L showing interface effect according to matching score
Value recommends the target object after being ranked up.
In one embodiment, the number of the showing interface effect for the target application recommended for the target object is more
It is a；Described device further include:
Third acquiring unit 705, for obtaining the first operation, first operation is for multiple showing interfaces from recommendation
A showing interface effect is selected in effect, as target interface bandwagon effect；
Display unit 706, for showing the target application according to the target interface bandwagon effect.
In one embodiment, the number of the showing interface effect for the target application recommended for the target object is one
It is a；Described device further include:
Display unit 706, for showing the target application according to the showing interface effect of recommendation.
It will be appreciated by those skilled in the art that the realization function of each unit in interface recommendation apparatus shown in Fig. 7 can join
According to foregoing interface recommended method associated description and understand.The function of each unit in interface recommendation apparatus shown in Fig. 7 can lead to
It crosses the program run on processor and realizes, can also be realized by specific logic circuit.
If the above-mentioned interface recommendation apparatus of the embodiment of the present application is realized in the form of software function module and as independence
Product when selling or using, also can store in a computer readable storage medium.Based on this understanding, this Shen
Please the technical solution of embodiment substantially the part that contributes to existing technology can body in the form of software products in other words
Reveal and, which is stored in a storage medium, including some instructions are with so that a computer is set
Standby (can be personal computer, server or network equipment etc.) executes the whole of each embodiment the method for the application
Or part.And storage medium above-mentioned includes: USB flash disk, mobile hard disk, read-only memory (ROM, Read Only Memory), magnetic
The various media that can store program code such as dish or CD.In this way, the embodiment of the present application be not limited to it is any specific hard
Part and software combine.
Correspondingly, the embodiment of the present application also provides a kind of computer program product, wherein being stored with, computer is executable to be referred to
It enables, which is performed the above-mentioned interface recommended method that can be realized the embodiment of the present application.
Fig. 8 is the structure composition schematic diagram of the computer equipment of the embodiment of the present application, as shown in figure 8, computer equipment 100
It may include that (processor 1002 can include but is not limited to micro process to one or more (one is only shown in figure) processors 1002
Device (MCU, Micro Controller Unit) or programmable logic device (FPGA, Field Programmable Gate
) etc. Array processing unit), memory 1004 for storing data and the transmitting device 1006 for communication function.
It will appreciated by the skilled person that structure shown in Fig. 8 is only to illustrate, the structure of above-mentioned electronic device is not made
At restriction.For example, computer equipment 100 may also include the more perhaps less component than shown in Fig. 8 or have and Fig. 8
Shown different configuration.
Memory 1004 can be used for storing the software program and module of application software, such as the method in the embodiment of the present application
Corresponding program instruction/module, the software program and module that processor 1002 is stored in memory 1004 by operation, from
And perform various functions application and data processing, that is, realize above-mentioned method.Memory 1004 may include high speed random storage
Device may also include nonvolatile memory, such as one or more magnetic storage device, flash memory or other are non-volatile solid
State memory.In some instances, memory 1004 can further comprise the memory remotely located relative to processor 1002,
These remote memories can pass through network connection to computer equipment 100.The example of above-mentioned network includes but is not limited to interconnect
Net, intranet, local area network, mobile radio communication and combinations thereof.
Transmitting device 1006 is used to that data to be received or sent via a network.Above-mentioned network specific example may include
The wireless network that the communication providers of computer equipment 100 provide.In an example, transmitting device 1006 includes a network
Adapter (NIC, Network Interface Controller), can be connected by base station with other network equipments so as to
It is communicated with internet.In an example, transmitting device 1006 can be radio frequency (RF, Radio Frequency) module,
It is used to wirelessly be communicated with internet.
It, in the absence of conflict, can be in any combination between technical solution documented by the embodiment of the present application.
In several embodiments provided herein, it should be understood that disclosed method and smart machine, Ke Yitong
Other modes are crossed to realize.Apparatus embodiments described above are merely indicative, for example, the division of the unit, only
Only a kind of logical function partition, there may be another division manner in actual implementation, such as: multiple units or components can be tied
It closes, or is desirably integrated into another system, or some features can be ignored or not executed.In addition, shown or discussed each group
Can be through some interfaces at the mutual coupling in part or direct-coupling or communication connection, equipment or unit it is indirect
Coupling or communication connection, can be electrical, mechanical or other forms.
Above-mentioned unit as illustrated by the separation member, which can be or may not be, to be physically separated, aobvious as unit
The component shown can be or may not be physical unit, it can and it is in one place, it may be distributed over multiple network lists
In member；Some or all of units can be selected to achieve the purpose of the solution of this embodiment according to the actual needs.
In addition, can be fully integrated into a second processing unit in each functional unit in each embodiment of the application,
It is also possible to each unit individually as a unit, can also be integrated in one unit with two or more units；
Above-mentioned integrated unit both can take the form of hardware realization, can also add the form of SFU software functional unit real using hardware
It is existing.
The above, the only specific embodiment of the application, but the protection scope of the application is not limited thereto, it is any
Those familiar with the art within the technical scope of the present application, can easily think of the change or the replacement, and should all contain
Lid is within the scope of protection of this application.
Claims (10)
1. a kind of interface recommended method, which is characterized in that the described method includes:
Acquire the image of target object；
The customer attribute information of the target object is obtained from the image of the target object；
Based on the customer attribute information of the target object, recommend the showing interface effect of target application for the target object.
2. the method according to claim 1, wherein described obtain the mesh from the image of the target object
Mark the customer attribute information of object, comprising:
Facial image is obtained from the image of the target object；
The facial image is analyzed, determines following at least one customer attribute information of the target object: Zhong Zuxin
Breath, gender information, age information, expression information, identification information.
3. according to the method described in claim 2, it is characterized in that, described analyze the facial image, described in determination
The age information of target object, comprising:
The facial image is analyzed, obtain the facial image estimates the age；
According to it is described estimate the age and with it is described estimate the age there are preset two or the above age gap away from year
In age, N width image pattern is chosen from the image pattern set at known age, the N is not less than 2；
Obtain the age size comparison result between the facial image and the N width image pattern of selection；
Probabilistic information is obtained according to the statistical information that the comparison result is formed, the probabilistic information is for determining the face figure
The age information of target object as in.
4. according to the method in any one of claims 1 to 3, which is characterized in that the use based on the target object
Family attribute information recommends the showing interface effect of target application for the target object, comprising:
In the corresponding multiple showing interface effects of target application, searches and match with the customer attribute information of the target object
N number of showing interface effect, N >=1；
N number of showing interface effect is recommended into the target object.
5. according to the method in any one of claims 1 to 3, which is characterized in that the use based on the target object
Family attribute information recommends the showing interface effect of target application for the target object, comprising:
In the corresponding multiple showing interface effects of target application, searches and match with the customer attribute information of the target object
N number of showing interface effect, N >=1；
M showing interface effect in N number of showing interface effect is recommended into the target object, 1≤M < N.
6. according to the method in any one of claims 1 to 3, which is characterized in that the use based on the target object
Family attribute information recommends the showing interface effect of target application for the target object, comprising:
The matching point of the corresponding multiple showing interface effects of target application is determined according to the customer attribute information of the target object
Numerical value；
The matching maximum L showing interface effect of fractional value, L >=1 are chosen from the multiple showing interface effect；
The L showing interface effect is recommended into the target object.
7. a kind of interface recommendation apparatus, which is characterized in that described device includes:
Acquisition unit, for acquiring the image of target object；
First acquisition unit, for obtaining the customer attribute information of the target object from the image of the target object；
Recommendation unit recommends target application for the customer attribute information based on the target object for the target object
Showing interface effect.
8. a kind of computer program product, which is characterized in that the computer program product includes computer executable instructions, should
After computer executable instructions are performed, method and step as claimed in any one of claims 1 to 6 can be realized.
9. a kind of storage medium, which is characterized in that be stored with executable instruction on the storage medium, which is located
Reason device realizes method and step as claimed in any one of claims 1 to 6 when executing.
10. a kind of computer equipment, which is characterized in that the computer equipment includes memory and processor, the memory
On be stored with computer executable instructions, can be realized when the processor runs the computer executable instructions on the memory
Method and step as claimed in any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910196544.2A CN109947510A (en) | 2019-03-15 | 2019-03-15 | A kind of interface recommended method and device, computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910196544.2A CN109947510A (en) | 2019-03-15 | 2019-03-15 | A kind of interface recommended method and device, computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109947510A true CN109947510A (en) | 2019-06-28 |
Family
ID=67010059
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910196544.2A Pending CN109947510A (en) | 2019-03-15 | 2019-03-15 | A kind of interface recommended method and device, computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109947510A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110309664A (en) * | 2019-07-05 | 2019-10-08 | 北京贝思科技术有限公司 | User's license control method and system |
| CN110908688A (en) * | 2019-11-26 | 2020-03-24 | 中国银行股份有限公司 | Application gray level publishing method and device |
| CN111309423A (en) * | 2020-02-13 | 2020-06-19 | 北京百度网讯科技有限公司 | Configuration method, device, equipment and medium of terminal interface image |
| WO2023020160A1 (en) * | 2021-08-20 | 2023-02-23 | 华为技术有限公司 | Recommendation method and apparatus, training method and apparatus, device, and recommendation system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106126687A (en) * | 2016-06-29 | 2016-11-16 | 北京小米移动软件有限公司 | Recommendation method, device, terminal and the server of interface subject |
| CN108399379A (en) * | 2017-08-11 | 2018-08-14 | 北京市商汤科技开发有限公司 | The method, apparatus and electronic equipment at facial age for identification |
-
2019
- 2019-03-15 CN CN201910196544.2A patent/CN109947510A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106126687A (en) * | 2016-06-29 | 2016-11-16 | 北京小米移动软件有限公司 | Recommendation method, device, terminal and the server of interface subject |
| CN108399379A (en) * | 2017-08-11 | 2018-08-14 | 北京市商汤科技开发有限公司 | The method, apparatus and electronic equipment at facial age for identification |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110309664A (en) * | 2019-07-05 | 2019-10-08 | 北京贝思科技术有限公司 | User's license control method and system |
| CN110908688A (en) * | 2019-11-26 | 2020-03-24 | 中国银行股份有限公司 | Application gray level publishing method and device |
| CN111309423A (en) * | 2020-02-13 | 2020-06-19 | 北京百度网讯科技有限公司 | Configuration method, device, equipment and medium of terminal interface image |
| CN111309423B (en) * | 2020-02-13 | 2023-11-21 | 北京百度网讯科技有限公司 | Terminal interface image configuration method, device, equipment and medium |
| WO2023020160A1 (en) * | 2021-08-20 | 2023-02-23 | 华为技术有限公司 | Recommendation method and apparatus, training method and apparatus, device, and recommendation system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11790589B1 (en) | System and method for creating avatars or animated sequences using human body features extracted from a still image | |
| US20220239988A1 (en) | Display method and apparatus for item information, device, and computer-readable storage medium | |
| CN110021061B (en) | Collocation model construction method, clothing recommendation method, device, medium and terminal | |
| CN109947510A (en) | A kind of interface recommended method and device, computer equipment | |
| CN108510437B (en) | Virtual image generation method, device, equipment and readable storage medium | |
| CN109635680B (en) | Multitask attribute identification method and device, electronic equipment and storage medium | |
| US10109051B1 (en) | Item recommendation based on feature match | |
| Escalera et al. | Chalearn looking at people and faces of the world: Face analysis workshop and challenge 2016 | |
| CN106294489B (en) | Content recommendation method, device and system | |
| CN109173263B (en) | Image data processing method and device | |
| US10083521B1 (en) | Content recommendation based on color match | |
| CN108234591A (en) | The content-data of identity-based verification device recommends method, apparatus and storage medium | |
| CN106202317A (en) | Method of Commodity Recommendation based on video and device | |
| CN110110118A (en) | Dressing recommended method, device, storage medium and mobile terminal | |
| CN109978975A (en) | A kind of moving method and device, computer equipment of movement | |
| CN108734557A (en) | Methods, devices and systems for generating dress ornament recommendation information | |
| EP3754587A1 (en) | Image/text-based design creating device and method | |
| CN106055710A (en) | Video-based commodity recommendation method and device | |
| CN109840793A (en) | Method for pushing and device, storage medium, the electronic device of promotion message | |
| CN109949116A (en) | Clothing matching recommended method, device, storage medium and mobile terminal | |
| US10818062B2 (en) | Crowdshaping realistic 3D avatars with words | |
| CN110266968B (en) | Method and device for making dancing video | |
| CN107665238A (en) | Image processing method and device, the device for picture processing | |
| CN110084657A (en) | A kind of method and apparatus for recommending dress ornament | |
| CN111311315A (en) | Video processing method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190628 |
|
| RJ01 | Rejection of invention patent application after publication |